Contraction rates and projection subspace estimation with Gaussian process priors in high dimension
Authors:
- 1 May 2026
- journal article
- Published by Bernoulli Society for Mathematical Statistics and Probability in Bernoulli
- Vol. 32 (2) , 1645-1664
Abstract
This work explores the dimension reduction problem for Bayesian nonparametric regression and density estimation. More precisely, we are interested in estimating a functional parameter f over the unit ball in Rd, which depends only on a d∗-dimensional subspace of Rd, with d∗<d. It is well-known that rescaled Gaussian process priors over a given function space achieve smoothness adaptation and posterior contraction with near minimax-optimal rates. Furthermore, hierarchical extensions of this approach, equipped with subspace projection, can also adapt to the intrinsic dimension d∗ (Tokdar (2011)). When the ambient dimension d does not vary with n, the minimax rate remains of the order n−β∕(2β+d∗), where β denotes the smoothness of f. However, this is up to multiplicative constants that can become prohibitively large as d increases. The dependence between the contraction rate and the ambient dimension has not been fully explored yet and this work provides a first insight: we let the dimensions d∗ and d grow with n, and by combining the arguments of Tokdar (2011) and Castillo and Randrianarisoa (2024), we derive growth rates for them that still lead to posterior consistency with minimax rate. We also discuss the optimality of the growth rate for d. Additionally, we provide a set of assumptions under which a consistent estimation of f leads to correct estimation of the subspace projection, assuming that d∗ is known.Keywords
This publication has 32 references indexed in Scilit:
- Posterior contraction rates for constrained deep Gaussian processes in density estimation and classificationCommunications in Statistics - Theory and Methods, 2024
- Subspace Estimation with Automatic Dimension and Variable Selection in Sufficient Dimension ReductionJournal of the American Statistical Association, 2022
- Efficient Manifold Approximation with SphereletsJournal of the Royal Statistical Society Series B: Statistical Methodology, 2022
- Graph Based Gaussian Processes on Restricted DomainsJournal of the Royal Statistical Society Series B: Statistical Methodology, 2021
- Sparse Sliced Inverse Regression via LassoJournal of the American Statistical Association, 2019
- Adaptive Bayesian multivariate density estimation with Dirichlet mixturesBiometrika, 2013
- Asymptotic Behaviour of the Posterior Distribution in Overfitted Mixture ModelsJournal of the Royal Statistical Society Series B: Statistical Methodology, 2011
- Regression Graphics1998
- Matrix Analysis1997
- On estimating a density using Hellinger distance and some other strange factsProbability Theory and Related Fields, 1986